Editor UX & Code Review
Editor and collaboration UX, including inline edits, chat layouts, file navigation, code review, browser previews, commits, and IDE performance.
28%
Best tweets about Cursor
50 Best Tweets About Cursor AI (2026)
Find the best tweets about Cursor AI, including coding workflows, agent features, editor tips, model comparisons, and developer experiments. Updated weekly.
Hands-on Cursor editor workflows and specific engineering outcomes rather than unrelated uses of the word cursor.
- Creators
- 42
- Updated
Original Xholic analysis
What 50 top Cursor posts reveal
Cursor discussion is predominantly supportive and hands-on: creators emphasize agent orchestration, editor review, scoped context, and shipping work across UI, automation, and product tasks. The main counterpoint is fit: model, interface, cost, context scale, and extension needs shape tool choice.
- Dominant tone
- Positive
- Median score
- 13.3
- Leading format
- Announcement
- Recent posts
- 32%
62% of posts
All-time engagement
100% of posts
Published in 90 days
Conversation map
The themes creators return to
Agent Orchestration & Cursor 3
Cursor 3’s agent-centric interface: parallel subagents, agent windows, cloud agents, branches, worktrees, voice, and managing autonomous coding tasks.
26%
Engineering Workflows & Outcomes
Hands-on experiences using Cursor to build, refactor, test, debug, polish UI, automate tasks, and ship production or client projects.
24%
Composer Models & Training
Composer model releases, training on product workflows, evaluation methodology, coding benchmarks, cost-performance tradeoffs, and reward hacking.
22%
Tool Comparisons & Adoption
Comparisons and tool-selection tradeoffs between Cursor and Claude Code, Codex, Windsurf, VS Code, Conductor, and other AI coding tools.
22%
MCP, Skills & Integrations
Cursor extensions, MCP integrations, skills, internal workflow kits, and tool-enabled agents for CI, testing, design, databases, and external services.
18%
Developer & Industry Impact
Broader implications of Cursor and coding agents for developer productivity, engineering practice, hiring, team economics, and AI-native software workflows.
16%
Workflow Setup & Context Management
Practical setup patterns for reliable Cursor work: persistent project instructions, rules, scoped context, incremental prompting, planning, and human review.
10%
Tone and stance
Sentiment Positive leads
Author posture Supportive leads
Performance benchmark
- Median likes
- 57
- Median reposts
- 3
- Median replies
- 9
- Median views
- 7.5K
Posts with media make up 58% of this collection. Their median all-time score is 9.40, compared with 15.6 for text-only posts.
Format mix
- Announcement 100% · score 13.3
Consensus and debate
Where creators agree, and where they do not
Shared view
Context is the operating discipline
Practical guidance favors scoped, staged work: persistent project instructions, file-level references, fresh chats, planning, and one feature per session rather than a single oversized prompt.
Shared view
Review stays central to agent workflows
Cursor is often presented as a review-oriented workflow: inspect diffs, ask why a change exists or request a fix, test from previews, and use quick accept/reject controls before committing or merging work.
Shared view
Workflows span build, polish, and automation
Hands-on accounts describe Cursor across landing pages, SEO fixes, internal tools, UI polish, and game features. One creator also switches models when a task needs stronger visual understanding.
Open debate
No single tool wins every workflow
Tool choice is presented as task-dependent. Some creators favor Cursor for persistent context and surgical edits, while others prefer Claude Code for larger refactors or use VS Code because of extension compatibility concerns.
Open debate
Praise comes with practical caveats
Positive reports include practical limits: weaker visual understanding than Opus for some work, degraded output in large codebases without careful context management, bugs, and out-of-pocket cost concerns.
Open debate
Agent-first UI is not universally preferred
The agent-window interface draws different preferences. One creator prefers retaining the old IDE-style view, while another favors a reduced interface centered on a sidebar, chat, and file editor.
What performs
Patterns behind standout posts
High-performing posts mix outcomes and implications
The five engagement outliers cover autonomous coordination, cloud-agent work, Composer 2.5 game development, engineering-practice discussion, and AI-assisted interviewing. Their all-time scores range from 270.04 to 1158.29.
UX narrowly leads the conversation
Editor UX and code review is the largest theme at 28% of posts (14 tweets), ahead of agent orchestration at 26% (13) and engineering workflows at 24% (12).
Setup advice is smaller but concrete
Workflow setup and context management accounts for 10% of posts (5 tweets). The cited posts offer specific practices including project instructions, scoped file context, fresh chats, staged planning, incremental work, and review.
Statistical standouts
- View standout post 1 Score 1158.3 · 87.29× median
- View standout post 2 Score 388.7 · 29.29× median
- View standout post 3 Score 313.2 · 23.6× median
- View standout post 4 Score 305.8 · 23.05× median
- View standout post 5 Score 270.0 · 20.35× median
Creator landscape
Who shapes this conversation
The five most represented creators account for 20% of the selected posts.
-
1. Vaishnavi
@_vmlops
2 posts
-
2. Richard Wu
@0xrwu
2 posts
-
3. Danny Limanseta
@DannyLimanseta
2 posts
-
4. Harshil Tomar
@Hartdrawss
2 posts
-
5. Anthony Kroeger
@kr0der
2 posts
-
6. Lee Robinson
@leerob
2 posts
Lee Robinson links usage to engineering practice
Lee Robinson has the highest median all-time score among the listed top voices, at 347.26. His posts combine cloud-agent and MCP examples with discussion of code-review implications.
Harshil Tomar emphasizes production guardrails
Harshil Tomar’s posts emphasize operational guardrails: CLAUDE.md-style project context, explicit security and quality rules, incremental scope, and review of generated files.
Danny Limanseta tests game-development flow
Danny Limanseta describes game-feature work with Composer 2.5 and highlights Cursor 3 interface elements including browse previews, debug-context shortcuts, commits, and rapid agent switching.
How this analysis was made
Themes, sentiment, stance, and post format are classified per tweet. All counts, shares, medians, creator concentration, freshness, and performance comparisons are then calculated directly from the published snapshot.
Xholic's all-time score compares engagement while accounting for reach, post age, and creator consistency. It is used for relative comparisons within this collection.
This report analyzes the exact 50-post snapshot shown below. AI identifies editorial categories and drafts explanations; all statistics are calculated from the snapshot, and every narrative claim is checked against cited posts before publication.
Best Cursor tweets
Top Cursor tweets from 42 creators
Ranked 01–50
- 01
@mntruell ·
We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution. Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days. This suggests that our technique for scaling agent coordination might generalize beyond coding.
- 02
@leerob ·
Cursor (and coding agents generally) still blows my mind daily. Just today: 1. I shipped a new landing page. I gave a 10min voice note to Cursor, left to go eat dinner, and came back to a 90% finished version. Made some small design and copy tweaks and merged. 2. Had Cursor dig through Search Console and Semrush with computer use, researched places we could improve SEO, and then merged 3 PRs with fixes. 3. Used the Supabase MCP to pull thousands of emails from the Compile waitlist, had it research them with web search based on ideal fit for the event, and got back a CSV with the top people to invite and why. 4. Updated an internal app I built for doing company-wide surveys (think Typeform but Cursor branded) in a few hours before our All Hands. 5. Had a few agents researching furniture I'm hoping to buy. They searched the web for a bunch of variants and then made a custom shopping cart (just an HTML page) with images, prices, links, and tons of details. Super helpful. I don't do this every day, of course, but it's still wild to me this is the new normal for what someone with a computer and AI can do. Most of these were running in the cloud as I was between meetings, just humming away in the background. I could check the app (🔜) to see progress and merge PRs. What a time to be alive. (P.S. if you extrapolated my usage today, I'd still be on the $200/mo plan)
- 03
@DannyLimanseta ·
After a couple more days with Composer 2.5, I've got a pretty good sense of what it can do for game dev, specifically this mouse cursor racing game I'm building. It nailed ~80% of the features I threw at it, from planning to execution. Pretty amazing. I did have to switch to Opus 4.7 MAX a few times for features that need stronger visual understanding, like adding a 360 loop to the track or nailing a specific visual effect I had in mind. But man, Opus 4.7 MAX is expensive. Composer 2.5's visual understanding is weaker than Opus 4.7, but for most other things it's pretty damn close, and 10x cheaper. So it's now my default. The beauty of Cursor is I can switch models whenever I want, so I'm never stuck on one. Really excited for the larger incoming model. I have a feeling it's going to shine at planning. Can't wait!
Watch video
- 04
@leerob ·
How are coding agents changing software engineering? Yapped for 15 minutes about new Cursor data we published, including: 1. Why lines of code is an imperfect measure of AI progress 2. Balancing intelligence/cost/speed for models 3. Code reviews with "Mega PRs" (1000+ lines)
Watch video
- 05
@ujjwalscript ·
Companies are moving from DSA rounds to AI rounds! Here’s a Modern TECH INTERVIEW: 1. The "Cursor" Pair-Programming Round Instead of a blank Google Doc, they give you an IDE fully loaded with an AI agent. The test isn't "Write this feature from scratch." The test is "Build this feature using the AI." They watch your workflow. Do you give the AI the right context? Do you blindly accept its autocomplete? […continued in thread below 👇]
- 06
@fredrikalindh ·
reviewing in cursor is now a much better experience than github - select diff and ask cursor why it's there (or to fix) - view videos/images of result - test straight from browser we also added mark as viewed, link to preview and many more improvements coming
Watch video
- 07
@tanayj ·
Good piece on the "war time" at Cursor. Some interesting quotes: - The company’s new mandate was labeled “P0 #1”—priority zero: “Build the best coding model.” - Cursor estimated last year that a $200-per-month Claude Code subscription could use up to $2,000 in compute, suggesting significant subsidization by Anthropic. Today, that subsidization appears to be even more aggressive, with that $200 plan able to consume about $5,000 in compute, according to a different person who has seen analyses on the company’s compute spend patterns. https://t.co/FaSFUuDvQv
- 08
@rvivek ·
Cursor’s founder on why AI makes the next engineer more valuable, not less. The New York Times spends ~$150M-$200M a year on software R&D, even though most people do not think of it as a software company. Professional software engineering is still far from solved because building a new codebase is not the same as safely migrating an existing system like Rippling’s 30M-line codebase, with years of logic, dependencies, and customer workflows behind it. Cursor’s 20-person support team handling millions of daily users clearly shows that AI leverage for small teams is real. But the scope of software work is still vast, so the ROI of adding the next strong engineer is higher, not lower.
Watch video
- 09
- 10
@asidorenko_ ·
Codex app/T3 Code/Conductor should copy the file panel from Cursor Glass New agentic IDEs still need a file view, even if a simplified one. Opening another app for this is too much friction. Cursor nailed the ux imo
Watch video
- 11
@DannyLimanseta ·
Redesigned the game's main menu today to give it a clean and cosy look and feel. I've been working with Cursor 3 for this game and I just wanted to give a shoutout to the folks at Cursor for making Cursor 3 so easy to use. IMO, Cursor 3 is the version of Cursor where I can get into a flow state very seamlessly. it's all down to the small touches. - The default browse preview and chat window layout is very easy to use. - Ability to send error/debug codes and prefill within the chat input field in a click of a button - One-click commit and push to Github - Ability to switch between agents almost instantly - even though this is not a cursor 3 thing, but being able to deploy everything to vercel with one click is a really nice touch. This is not a sponsored post, but I have been using Cursor for ~11 months now and I have been very happy with my experience with it. Just a note that I am not a progammer, so the removal of the code sections from Cursor 3 didn't matter to me since the code is all greek to me anyway.
Watch video
- 12
@jshguo ·
Most designers don’t realize how strong Codex's visual capabilities are. I’ve tested this for months. Give it a screenshot, ask it to rebuild the UI in Framer, and the result is often surprisingly close. I also usually keep two agents working on the same project at the same time: one Codex, one Cursor. Cursor is better for implementation flow. Codex is surprisingly strong at reading visual references, understanding layout, spacing, hierarchy, and rebuilding the structure. They complement each other.
- 13
- 14
@0xrwu ·
First impressions of Cursor 3 vs @conductor_build: +1 for Cursor: - Cloud Agents: really nice to not have to worry about Mac going to sleep - Better file editor + global file search - Built-in browser (haven't used much yet, but seems convenient) +1 for Conductor: - (10x this) can use Codex/Claude subscriptions - Tabs: multiple sessions for the same worktree/session - Worktrees auto-fetch from origin - Better GHA status UX - Better hotkeys I think ultimately Cursor will win with enterprises, whereas Conductor is the choice for the few-man teams.
- 15
- 16
@mark_k ·
Why I think the SpaceX / Cursor merger is a big deal for both companies: @cursor_ai already has one of the best AI coding products in the world, but the next step is brutally expensive: frontier-level model training, massive compute, and a much tighter loop between product usage and model improvement. SpaceXAI brings exactly that. Compute, Grok, infrastructure, and the willingness to train huge models directly around real product needs instead of treating coding as just another benchmark category. And Cursor brings something equally valuable: distribution into serious developer workflows. Not toy prompts, not leaderboard tasks, but millions of real edits, refactors, bug fixes, rejections, and taste signals from engineers using the product every day. That is why the upcoming 1.5T Grok model trained together with the Cursor team and their data is so interesting. This is not just "Grok inside an editor". It is potentially the beginning of a very strong feedback loop: better model → better Cursor → more expert usage → better training data → better model. If they execute, Cursor can become much more than an AI editor. It can become the front end for one of the strongest coding and knowledge-work AI stacks in the world. Very bullish on this.
- 17
@nikita_builds ·
Holy sht, it just clicked for me Cursor can kill Github There's a few layers to this - Microsoft was LOOKING to put a bid on Cursor, but they walked. - Cursor made a deal with xAI instead - OpenAI acquired Windsurf - Musk <> Altman beef First, how would they do it: - prefer "cursorgit" by default in cursor ide - repurpose/clone cloud agents infrastructure infra to be gh actions runtime equivalent - undercut actions pricing by offering unlimited minutes (they make money on bugbot/cloud agents anyway) - add one command “cursor migrate <repo>” to the cli - OSS initiative “clone your issue/comment history + stars” Why it makes so much sense: - Sentiment around Github is terrible right now - SpaceX/xAI planning to go public - Microsoft is OpenAI's largest investor, Musk can eat their market share - xAI holds a 6-month call option: acquire Cursor for $60B or pay $10B for collaboration. The $10B is guaranteed
- 18
@jarrodwatts ·
Cursor → Claude Code/Codex → Cursor I’m noticing devs going full circle lately - back to Cursor. IMO, this stems from the lethargic feeling you get when you try to outsource your thinking to the LLM too much. It’s an unusual feeling shipping code you don’t look at, especially now that it has such a low cost to change/delete later. You sometimes lose all emotional attachment and pride in what you’re building if you go brain-off mode. The best way I’ve found to avoid this (which is quite difficult) is to work on multiple things at once. Don’t swap from Claude Code to Twitter - instead, use worktrees to work on a different feature or just work another project entirely in parallel. This context switching is mentally draining, but it importantly allows you to stay focused. You can do this with any tool you want (I personally use all three of them in different ways). Cursor is likely easiest as it’s the most familiar workflow to what you’re already used to.
- 19
- 20
@bridgemindai ·
5 Claude Opus 4.6 subagents running inside Cursor 3. All analyzing my codebase at the same time. This is insane. One prompt. Five agents launched. All completed. Dead code found. Security vulnerabilities flagged. Entire codebase reviewed in minutes. Cursor 3 with Claude Opus 4.6 Max is one of the most productive vibe coding tools I've used. The design upgrade alone makes this worth it. Managing subagents in Cursor feels like a completely different product than it was a week ago.
- 21
@tanayj ·
Cursor's Composer 2 technical report is fantastic. Some of my notes: - Base model is Kimi K2.5. Also Considered GLM‑5, Deepseek v3.2 - Two-stage training: continued pretraining on code-heavy data, then large-scale RL - Tasks used for RL were based on representative Cursor usage (iterating on features, debugging most represented) - Training stack built on Ray + PyTorch. Fully asynchronous with independent training and rollout generation workers - RL Training environments run on Firecracker VMs via an internal platform called Anyrun - RL inference runs on Fireworks AI - Developed own evals (Cursorbench-3) where tasks require ~10x more lines changed and have shorter instructions than SWE-bench - Composer2 is close to SOTA on their evals and much cheaper than other models with similar performance
- 22
@Hartdrawss ·
The exact CURSOR setup that makes vibe coding production-ready : Most people use Cursor like a smarter autocomplete. Here's the full setup I use on every client project: CLAUDE.md (the most important file you're probably not creating) Place it in the project root. Cursor reads it automatically and applies it to every prompt. Include these four sections: STACK — Full tech stack with exact versions. Which library handles what. What you explicitly don't use. CONVENTIONS — Folder structure with examples. Naming rules for files, functions, variables. Error handling pattern. API response format. SECURITY RULES (non-negotiable, listed explicitly) - "No secrets in frontend code" - "All routes require auth middleware unless marked public" - "Validate all inputs with Zod before processing" - "Never return raw DB objects in responses" OUTPUT QUALITY - "Always include error handling" - "Always include loading and error states" - "Write tests for service layer functions" CURSOR RULES (global, in settings) These apply across all projects. Mine include: - "Always use async/await not .then chains" - "Prefer const. Never use var." - "Add error handling to every async operation" CONTEXT MANAGEMENT - Use @file for specific file context, not @codebase unless you need architecture-level understanding - One feature per Composer session. Don't mix concerns. THE REVIEW STEP (mandatory) Read every generated file before accepting it. AI makes mistakes that look correct. The ones you miss ship to production. That's the entire setup.
- 23
@Layton_Gott ·
Cursor just showed the new AI coding playbook... Take the best open base. Train it inside your product. Optimize for your actual workflow. Price it low enough that people stop thinking before they use it. That's Cursor's new model Composer 2.5. Kimi K2.5 base. Cursor training + RL on top. 69.3 Terminal-Bench. 79.8 SWE-bench Multilingual. 63.2 CursorBench. $0.50/M input. $2.50/M output. Roughly 10x cheaper than Opus 4.7 and 2-3x cheaper than GPT-5.5 at close to the same coding scores. App companies just realized they don't have to wait for frontier labs forever. If the app owns the workflow, the app can train the model around the work.
- 24
- 25
@seunosewa ·
Cursor Composer 2.5: 1. Proves that you don't need to train a model from scratch. Best to take a good open source model and just keep training it more and more. 2. Is a big problem for the frontier AI companies. Cursor has the best UX for AI coding and now it's the most economical. People are starting to notice. 3. What looks good: a) $20 claude-pro/chatgpt-plus with $60 cursor. b) Just cursor. $20, $60, $200, since Cursor also provides frontier models.
- 26
@kr0der ·
i gave Cursor 3 another try and i have to say it's a really really good multi-agent interface it's very performant - pretty much no lag at all, almost no UI glitches, and everything appears instantly from an unbiased POV because i use both Cursor and Codex, the Cursor 3 app is slightly better in terms of performance/features, but a huge update is coming to Codex soon so we'll see either way both are great to use and i'm happy using both
- 27
@prasenx ·
Cursor's Composer 2.5 got so smart, it started cheating. → during training it was solving every task thrown at it → so Cursor made the tasks harder with 25x more synthetic problems → the model started finding shortcuts instead of solving them properly → it reverse-engineered a Python type-checking cache to recover deleted code → it decompiled Java bytecode to reconstruct a third-party API → Cursor had to build monitoring tools just to catch it → they call it "reward hacking" the AI gaming its own training the AI wasn't just learning to code, it was learning to cheat.
Watch video
- 28
@rryssf ·
Cursor just built their own AI model. It beats Claude Opus 4.6 on real-world coding tasks and costs a fraction of the price. > Composer 2 scores 61.3% on CursorBench versus Opus 4.6's 58.2%. Same tasks. Cheaper inference. Built specifically for the work developers actually do. > Cursor didn't benchmark Composer 2 on SWE-bench. They built their own evaluation suite from actual coding sessions run by their engineering team. > CursorBench tasks have a median of 181 lines changed per task versus 7 to 10 lines for SWE-bench Verified. Prompts are deliberately underspecified, averaging 390 characters versus 1,185 to 3,055 characters for public benchmarks. The agent receives a terse bug report, a reference to production logs, and a codebase. No hand-holding. No narrow specification. Figure out what's broken and fix it. That's what real software engineering looks like. That's what Composer 2 was trained on. > The architecture is a 1.04 trillion parameter Mixture-of-Experts model with 32 billion active parameters, starting from Kimi K2.5 as the base. Cursor ran continued pretraining on a large code-dominated data mix, extending context to 256k tokens, then applied large-scale reinforcement learning on tasks that directly emulate real Cursor sessions the same tools, the same harness, the same environment the deployed model runs in. The RL training distribution covers debugging, new features, refactoring, codebase understanding, testing, code review, optimization, DevOps, and migration. > Not just bug fixes. The full spectrum of what developers actually ask an agent to do. > The infrastructure finding is what separates this from standard fine-tuning. Cursor trained with weight updates mid-rollout inference workers update weights while a trajectory is still being generated, so later tokens in a rollout are less off-policy. They replay MoE expert routing from inference to training to eliminate numerical disagreement between the two forward passes. They compress weight updates to diffs rather than full parameter uploads, getting the 1T parameter model's updates down to a few gigabytes per sync. The entire RL pipeline ran across 3 GPU regions and 4 CPU regions simultaneously. The full benchmark results: → Composer 2 on CursorBench: 61.3% vs Opus 4.6's 58.2% → Composer 2 on SWE-bench Multilingual: 73.7% vs Opus 4.6's 75.8% → Composer 2 on Terminal-Bench: 61.7% vs Opus 4.6's 58.0% → 37% relative improvement over Composer 1.5 on CursorBench → 61% improvement over Composer 1 → CursorBench tasks: median 181 lines changed vs 7-10 for SWE-bench → Inference cost: Pareto-optimal accuracy competitive with frontier, cost comparable to smaller models → Both average performance AND best-of-K improve during RL training no diversity tradeoff > The result challenges a core assumption about frontier AI. The default strategy has been to use the biggest general-purpose model available and prompt it well. Cursor's finding is that a model trained specifically on your domain, your tools, your task distribution, and your harness outperforms general models that cost significantly more to run. The gap between Composer 2 and Opus 4.6 on CursorBench is not marginal. It's consistent across the full evaluation set. And Composer 2 gets there at lower inference cost. > OpenAI suspended SWE-bench Verified reporting after finding evidence that frontier models could generate gold patches from memory. Haiku 4.5 scores 73.3% on SWE-bench Verified nearly identical to GPT-5's 74.9% despite the two models performing very differently on broader task distributions. The benchmarks that the industry uses to compare coding models are contaminated, narrow, and increasingly disconnected from what developers actually need. Cursor built a benchmark that isn't. Then they built a model that wins on it. Domain specialization just beat general intelligence. And it did it cheaper.
- 29
- 30
@ttunguz ·
Last week, Cursor launched Composer 2 to over one million daily active users. Within hours, a developer discovered Cursor had built its flagship model on top of Moonshot AI’s Kimi K2.5, a Chinese open-source model. Moonshot AI’s response? “This is the open model ecosystem we love to support.” Cursor’s model is at near parity with state-of-the-art at one-eighth the price. It’s also no coincidence the editor powering Cursor is open-source, VS Code. $50B in market cap on open-source foundations. Open source empowers startups to compete with incumbents.
- 31
@toolfolio ·
Cursor 3 keeps getting better.. + You can now split agents like terminals and run multiple tasks in parallel + Talk to Cursor with voice (hold Ctrl+M) + Jump from diffs straight into code + Choose which branch agents run on + Filter workspace search They’ve also improved performance with 87% fewer dropped frames on large edits
Watch video
- 32
@RoundtableSpace ·
CURSOR DESIGN IS REAL NOW AND IT JUST GOT OPEN SOURCED FOR EVERYONE Point, comment, mark, edit, capture and remix. Let AI design everything, take control whenever you want.
Watch video
- 33
@mark_k ·
Cursor just released Composer 2.5. 🔥 What stands out to me is that this is not just about better benchmark numbers. @cursor_ai seem to be focusing on the parts you actually feel when using an agent all day: handling longer tasks, following complex instructions, collaborating more smoothly, and getting in the way less often. Also notable: Cursor says they are training a much larger model from scratch together with SpaceXAI, using 10x more total compute and Colossus 2’s million H100-equivalents. The coding agent space is getting very serious now. Cursor is not just building an IDE anymore. They are building the model layer underneath it.
- 34
@enesakar ·
Yesterday, I moved from cursor to vs code. why: - I use claude/codex inside cursor for a long time. it looks ide + agent separation is the way. - I realised that i have not used any cursor specfic features for a long time. tab based auto complete is not valuable anymore. - I could use claude under cursor, but some extensions had issues (github pr) in cursor. Why would i use a clone instead of the real one.
- 35
- 36
@neseliol ·
I use Cursor mostly for vibe coding. Learning, experimenting, building basic stuff. Set up Aptos MCP and it genuinely made the AI more useful for Aptos/Move: less guessing, better examples, more accurate tooling answers. Cursor’s AI works much better with Aptos now. Worth trying. 👉 https://t.co/tFocn3KyCw
- 37
@JJEnglert ·
I was building in @cursor_ai again yesterday. First time being back there in a while. Here are my thoughts: - Composer 2 is VERY fast. - I still really love using Cursor for UI edits / tweaks / polishing. Fantastic UX and super fast. - Using the @pencildev MCP within Cursor is a cheatcode. - I love being able to throw different models at the problem, especially gemini pro 3.1 since it's the best model by far when it comes to UI / UX. - So easy to spin up multiple agents. You can do this in every platform, but given cursors speed, this really shines here. Generally, I enjoyed myself there. I'll be back again for my UI work!
- 38
- 39
@vtemian ·
https://t.co/BRojPmyWf3 watch what your AI coding agents are doing, in real-time. a TypeScript library that turns Cursor and Claude Code sessions into a stream of events no plugins, no setup. just point it at your workspace https://t.co/oo7pskR9fk
Watch video
- 40
- 41
@Hartdrawss ·
Cursor vs. Windsurf for building in 2026 : Here's the FULL breakdown. 1/ CURSOR Where it wins: > CLAUDE[.]md is a genuine game changer. Project-level context that persists across every session. > Composer 2 handles multi-file edits and refactors reliably > More control over context: you choose exactly what AI sees > Feels like an IDE that added AI, not an AI that added an IDE Where it falls short: > Large codebases need careful context management or output degrades > Autocomplete occasionally suggests wrong things with high confidence 2/ WINDSURF Where it wins: > Cascade (their agentic flow) handles autonomous multi-step tasks better than anything in Cursor > Slightly better at understanding intent without detailed instruction > The UI feels more fluid for rapid iteration Where it falls short: > Less control over the context window > No equivalent of CLAUDE.md (project-level persistent instructions) > Smaller community = fewer tips and real-world patterns MY VERDICT: I use Cursor as my daily driver. The CLAUDE[.]md alone keeps me there. Windsurf is worth trying for projects where you want the AI to be more autonomous on a well-defined task.
- 42
@jayjanyani ·
The honest AI coding tool cheatsheet ( 2026 ) : what i actually reach for, and when : Claude Code -> best for big multi-file changes and agentic work in the terminal. my daily driver. Cursor -> fastest inline editing + Tab autocomplete. great for surgical edits, strains on huge refactors. Windsurf -> Cursor alternative with better whole-codebase context. Cline -> best free VS Code extension for agentic coding, bring your own key. v0 -> UI mockup to React in 2 minutes. paste a screenshot, get components. Lovable -> fastest idea-to-live-app for non-coders, full stack generated. Bolt -> quick prototypes in-browser, falls over past MVP size. Aider -> terminal AI that's git-aware, commits each change cleanly. GitHub Copilot -> autocomplete only now. outclassed for anything agentic. MY ACTUAL SETUP > Claude Code for building + refactoring > Cursor Tab for the fast inline stuff > v0 when i need UI fast one tool won't do everything. stop hunting for the ONE. stack the right 2-3.
- 43
@0xrwu ·
The new Cursor 3 Agent Windows is the epitome of this whole AI software wave: the best vibe-coded software is its simplest reduced form. Cursor basically ripped out all of VSCode and just kept: 1. the agent sidebar (w/ project hierarchy) 2. the chat window 3. file editor Nothing else matters. You don't need plugins if an agent does everything with skills/tools. Debug console? Forget about it. 1000 different settings for the editor? You just need 20. In fact, the best software I've used post-vibe slop days tend to have a few buttons you click 80% of the time, vs 100 buttons you click 5% of the time (if at all). Less is more!
- 44
@JulianGoldieSEO ·
This might be the biggest shift in coding since ChatGPT launched. Cursor 3 lets you open an agents window, describe what you want built, and watch an AI agent handle the code, testing, errors, and pull request. The crazy part? You do not manage files anymore. You manage agents.
Watch video
- 45
@_vmlops ·
SOMEONE JUST DROPPED A SKILLS LIST FOR CURSOR most skill repos just teach the agent a task and stop there. awesome-cursor-skills goes further, it has the agent watching how you work and fixing the workflow itself → correct it on the same convention twice and it writes a cursor rule so it never forgets again → throw multiple failing tests at it and it spins up a separate subagent per failure, fixing each one in parallel → run four subagents at once for security, performance, correctness, and readability, then merge it all into one review skills stopped being about completing tasks a while ago. now they're about noticing patterns and closing the loop themselves
- 46
- 47
@_vmlops ·
CURSOR OPEN-SOURCED THEIR OWN INTERNAL DEV WORKFLOWS this is the actual plugin kit Cursor's own team uses to ship code → ci-watcher agent that monitors PR checks and reports pass/fail automatically → control-cli and control-ui skills to drive and inspect CLIs/UIs without third-party tools → deslop, a skill built specifically to clean up AI-generated code smell → fix-ci finds failing checks, reads logs, applies targeted fixes → 17 skills and 2 rules total, all built to work with zero external service dependencies not a demo repo. this is what runs inside Cursor everyday
- 48
@rfradin ·
4 months ago, Cursor was everywhere. Since then, 40% of a cohort we tracked moved to other tools like Claude Code or Codex. But this isn't bad news for Cursor, believe it or not. The 60% that remained on Cursor tripled their usage. I'd expect a similar story with Codex in a month or two. Once a team finds their tool, they go all-in, and get more productive. You can't find this out without measuring it. Great excerpt from our AI webinar yesterday.
Watch video
- 49
@kr0der ·
used a bit of Cursor again today and it’s actually really good - i still love the CMD Y/CMD N flow in the IDE since it makes reviewing AI code at least 2x faster i haven’t been using the agents window much since tsgo is bugged there, but a fix is coming very soon, so i’ll probably try that out again i still think the only downside for me is that it’s expensive, especially if you pay for AI out of pocket in terms of the best AI coding tool, from what i’ve tried i’d say the Codex and Cursor apps are pretty equal: - Codex app has the best computer use, great worktree support, and obviously the subsidised subscription - Cursor’s app is less laggy and less buggy, and has the best cloud support
- 50
Best Tweets by Topic